Enhancing Cloud Data Security using Artificial Neural Networks for Users’ Account Hijacking Security Threats

Objectives: To ensure the security of passwords of cloud users' accounts that cannot be decrypted easily by any software or hackers. Methods: In this manuscript, we have designed an experimental setup using a feed-forward back-propagation algorithm of Artificial Neural Networks techniques to ensure cloud data security. For this purpose, we have utilized password-based datasets created by us. 70% of the datasets are allocated for training and 30% for testing and validation purposes. In this training, TRAINLM training function, LEARNGDM adaptive function, performance function is MSE, and PURELIN and TANSIG transfer function to transfer the neurons from input to hidden layer and hidden to the output layer has been used. The minimum learning rate is set to 0.001. Findings: A username and password are required to access cloud services. A cloud-based storage system is used to store login credentials. Due to inadequate security, attackers use hacking techniques to gain access to users’ accounts. Attackers steal data, resources, or services from these accounts. To ensure the security of passwords of cloud users' accounts, we have designed an experimental setup using a feed-forward back-propagation algorithm of neural network techniques. Through this approach, the passwords are stored in a weight matrix, which is a multi-dimensional structure. Novelty: The dimensions of the weight matrix are obscured, making it impossible for the hackers to determine its structure. As a result, we conclude that cloud data is effectively secured on the cloud server. Keywords: Artificial Neural Networks, Cloud Computing, Data Security, Feed-Forward Back-Propagation Algorithm, Machine Learning